3 accepted papers
Reinforcement post training (RPT) has recently shown promise in improving the reasoning abilities of large language models (LLMs). However, it remains unclear how well these improvements generalize to new domains, as prior work evaluates RPT models on data from the same domains used for fine-tuning.…
Future advanced AI systems may learn sophisticated strategies through reinforcement learning (RL) that humans cannot understand well enough to safely evaluate. We propose a training method which avoids agents learning undesired multi-step plans that receive high reward (multi-step "reward hacks") ev…
Many machine learning applications rely on large datasets that are conveniently collected from existing sources or that are labeled automatically as a by-product of user actions. However, in settings such as content moderation, accurately and reliably labeled data comes at substantial cost. If a lea…